From Zero to Hero: Cold-Start Anomaly Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917679542042624 |
|---|---|
| author | Reiss, Tal Kour, George Zwerdling, Naama Anaby-Tavor, Ateret Hoshen, Yedid |
| author_facet | Reiss, Tal Kour, George Zwerdling, Naama Anaby-Tavor, Ateret Hoshen, Yedid |
| contents | When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such "cold-start" cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20341 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Zero to Hero: Cold-Start Anomaly Detection Reiss, Tal Kour, George Zwerdling, Naama Anaby-Tavor, Ateret Hoshen, Yedid Machine Learning Computation and Language When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such "cold-start" cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics. |
| title | From Zero to Hero: Cold-Start Anomaly Detection |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2405.20341 |